© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-32K
    6. 3344
    Prev
    Next
    INDEX
    Explanations

    phrases related to breaks or pauses in time, often associated with personal or professional hiatuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    سر
    -0.13
     dawn
    -0.13
     Darwin
    -0.13
    weep
    -0.13
     Dawn
    -0.12
    RowCount
    -0.12
    indsight
    -0.12
    é»ŀ
    -0.12
    Utf
    -0.12
    Æ°á»Ľ
    -0.12
    POSITIVE LOGITS
     hiatus
    0.51
     break
    0.51
     pause
    0.48
     breaks
    0.43
    ä¼ij
    0.43
    pause
    0.41
     Pause
    0.40
     pauses
    0.38
    Pause
    0.38
     Break
    0.38
    Activations Density 0.248%

    No Known Activations